summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorJakub Kicinski <kuba@kernel.org>2021-09-24 17:27:19 -0700
committerJakub Kicinski <kuba@kernel.org>2021-09-24 17:27:20 -0700
commit7fe7f3182a0dd8f9bad463598ed103b3d8cfa739 (patch)
treeee1487602916de805486c351f396cb858cea4978 /net
parent4526fe74c3c5095cc55931a3a6fb4932f9e06002 (diff)
parente9edc188fc76499b0b9bd60364084037f6d03773 (diff)
Merge git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf
Pablo Neira Ayuso says: ==================== Netfilter/IPVS fixes for net 1) ipset limits the max allocatable memory via kvmalloc() to MAX_INT, from Jozsef Kadlecsik. 2) Check ip_vs_conn_tab_bits value to be in the range specified in Kconfig, from Andrea Claudi. 3) Initialize fragment offset in ip6tables, from Jeremy Sowden. 4) Make conntrack hash chain length random, from Florian Westphal. 5) Add zone ID to conntrack and NAT hashtuple again, also from Florian. 6) Add selftests for bidirectional zone support and colliding tuples, from Florian Westphal. 7) Unlink table before synchronize_rcu when cleaning tables with owner, from Florian. 8) ipset limits the max allocatable memory via kvmalloc() to MAX_INT. 9) Release conntrack entries via workqueue in masquerade, from Florian. 10) Fix bogus net_init in iptables raw table definition, also from Florian. 11) Work around missing softdep in log extensions, from Florian Westphal. 12) Serialize hash resizes and cleanups with mutex, from Eric Dumazet. * git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf: netfilter: conntrack: serialize hash resizes and cleanups netfilter: log: work around missing softdep backend module netfilter: iptable_raw: drop bogus net_init annotation netfilter: nf_nat_masquerade: defer conntrack walk to work queue netfilter: nf_nat_masquerade: make async masq_inet6_event handling generic netfilter: nf_tables: Fix oversized kvmalloc() calls netfilter: nf_tables: unlink table before deleting it selftests: netfilter: add zone stress test with colliding tuples selftests: netfilter: add selftest for directional zone support netfilter: nat: include zone id in nat table hash again netfilter: conntrack: include zone id in tuple hash again netfilter: conntrack: make max chain length random netfilter: ip6_tables: zero-initialize fragment offset ipvs: check that ip_vs_conn_tab_bits is between 8 and 20 netfilter: ipset: Fix oversized kvmalloc() calls ==================== Link: https://lore.kernel.org/r/20210924221113.348767-1-pablo@netfilter.org Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'net')
-rw-r--r--net/ipv4/netfilter/iptable_raw.c2
-rw-r--r--net/ipv6/netfilter/ip6_tables.c1
-rw-r--r--net/netfilter/ipset/ip_set_hash_gen.h4
-rw-r--r--net/netfilter/ipvs/ip_vs_conn.c4
-rw-r--r--net/netfilter/nf_conntrack_core.c154
-rw-r--r--net/netfilter/nf_nat_core.c17
-rw-r--r--net/netfilter/nf_nat_masquerade.c168
-rw-r--r--net/netfilter/nf_tables_api.c30
-rw-r--r--net/netfilter/nft_compat.c17
-rw-r--r--net/netfilter/xt_LOG.c10
-rw-r--r--net/netfilter/xt_NFLOG.c10
11 files changed, 270 insertions, 147 deletions
diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c
index b88e0f36cd05..8265c6765705 100644
--- a/net/ipv4/netfilter/iptable_raw.c
+++ b/net/ipv4/netfilter/iptable_raw.c
@@ -42,7 +42,7 @@ iptable_raw_hook(void *priv, struct sk_buff *skb,
static struct nf_hook_ops *rawtable_ops __read_mostly;
-static int __net_init iptable_raw_table_init(struct net *net)
+static int iptable_raw_table_init(struct net *net)
{
struct ipt_replace *repl;
const struct xt_table *table = &packet_raw;
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index de2cf3943b91..a579ea14a69b 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -273,6 +273,7 @@ ip6t_do_table(struct sk_buff *skb,
* things we don't know, ie. tcp syn flag or ports). If the
* rule is also a fragment-specific rule, non-fragments won't
* match it. */
+ acpar.fragoff = 0;
acpar.hotdrop = false;
acpar.state = state;
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index 6186358eac7c..6e391308431d 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -130,11 +130,11 @@ htable_size(u8 hbits)
{
size_t hsize;
- /* We must fit both into u32 in jhash and size_t */
+ /* We must fit both into u32 in jhash and INT_MAX in kvmalloc_node() */
if (hbits > 31)
return 0;
hsize = jhash_size(hbits);
- if ((((size_t)-1) - sizeof(struct htable)) / sizeof(struct hbucket *)
+ if ((INT_MAX - sizeof(struct htable)) / sizeof(struct hbucket *)
< hsize)
return 0;
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index c100c6b112c8..2c467c422dc6 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -1468,6 +1468,10 @@ int __init ip_vs_conn_init(void)
int idx;
/* Compute size and mask */
+ if (ip_vs_conn_tab_bits < 8 || ip_vs_conn_tab_bits > 20) {
+ pr_info("conn_tab_bits not in [8, 20]. Using default value\n");
+ ip_vs_conn_tab_bits = CONFIG_IP_VS_TAB_BITS;
+ }
ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits;
ip_vs_conn_tab_mask = ip_vs_conn_tab_size - 1;
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 94e18fb9690d..770a63103c7a 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -74,10 +74,14 @@ static __read_mostly struct kmem_cache *nf_conntrack_cachep;
static DEFINE_SPINLOCK(nf_conntrack_locks_all_lock);
static __read_mostly bool nf_conntrack_locks_all;
+/* serialize hash resizes and nf_ct_iterate_cleanup */
+static DEFINE_MUTEX(nf_conntrack_mutex);
+
#define GC_SCAN_INTERVAL (120u * HZ)
#define GC_SCAN_MAX_DURATION msecs_to_jiffies(10)
-#define MAX_CHAINLEN 64u
+#define MIN_CHAINLEN 8u
+#define MAX_CHAINLEN (32u - MIN_CHAINLEN)
static struct conntrack_gc_work conntrack_gc_work;
@@ -188,11 +192,13 @@ seqcount_spinlock_t nf_conntrack_generation __read_mostly;
static siphash_key_t nf_conntrack_hash_rnd __read_mostly;
static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple,
+ unsigned int zoneid,
const struct net *net)
{
struct {
struct nf_conntrack_man src;
union nf_inet_addr dst_addr;
+ unsigned int zone;
u32 net_mix;
u16 dport;
u16 proto;
@@ -205,6 +211,7 @@ static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple,
/* The direction must be ignored, so handle usable members manually. */
combined.src = tuple->src;
combined.dst_addr = tuple->dst.u3;
+ combined.zone = zoneid;
combined.net_mix = net_hash_mix(net);
combined.dport = (__force __u16)tuple->dst.u.all;
combined.proto = tuple->dst.protonum;
@@ -219,15 +226,17 @@ static u32 scale_hash(u32 hash)
static u32 __hash_conntrack(const struct net *net,
const struct nf_conntrack_tuple *tuple,
+ unsigned int zoneid,
unsigned int size)
{
- return reciprocal_scale(hash_conntrack_raw(tuple, net), size);
+ return reciprocal_scale(hash_conntrack_raw(tuple, zoneid, net), size);
}
static u32 hash_conntrack(const struct net *net,
- const struct nf_conntrack_tuple *tuple)
+ const struct nf_conntrack_tuple *tuple,
+ unsigned int zoneid)
{
- return scale_hash(hash_conntrack_raw(tuple, net));
+ return scale_hash(hash_conntrack_raw(tuple, zoneid, net));
}
static bool nf_ct_get_tuple_ports(const struct sk_buff *skb,
@@ -650,9 +659,11 @@ static void nf_ct_delete_from_lists(struct nf_conn *ct)
do {
sequence = read_seqcount_begin(&nf_conntrack_generation);
hash = hash_conntrack(net,
- &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
+ &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
+ nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_ORIGINAL));
reply_hash = hash_conntrack(net,
- &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
+ &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
+ nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_REPLY));
} while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));
clean_from_lists(ct);
@@ -819,8 +830,20 @@ struct nf_conntrack_tuple_hash *
nf_conntrack_find_get(struct net *net, const struct nf_conntrack_zone *zone,
const struct nf_conntrack_tuple *tuple)
{
- return __nf_conntrack_find_get(net, zone, tuple,
- hash_conntrack_raw(tuple, net));
+ unsigned int rid, zone_id = nf_ct_zone_id(zone, IP_CT_DIR_ORIGINAL);
+ struct nf_conntrack_tuple_hash *thash;
+
+ thash = __nf_conntrack_find_get(net, zone, tuple,
+ hash_conntrack_raw(tuple, zone_id, net));
+
+ if (thash)
+ return thash;
+
+ rid = nf_ct_zone_id(zone, IP_CT_DIR_REPLY);
+ if (rid != zone_id)
+ return __nf_conntrack_find_get(net, zone, tuple,
+ hash_conntrack_raw(tuple, rid, net));
+ return thash;
}
EXPORT_SYMBOL_GPL(nf_conntrack_find_get);
@@ -842,6 +865,7 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct)
unsigned int hash, reply_hash;
struct nf_conntrack_tuple_hash *h;
struct hlist_nulls_node *n;
+ unsigned int max_chainlen;
unsigned int chainlen = 0;
unsigned int sequence;
int err = -EEXIST;
@@ -852,18 +876,22 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct)
do {
sequence = read_seqcount_begin(&nf_conntrack_generation);
hash = hash_conntrack(net,
- &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
+ &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
+ nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_ORIGINAL));
reply_hash = hash_conntrack(net,
- &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
+ &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
+ nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_REPLY));
} while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));
+ max_chainlen = MIN_CHAINLEN + prandom_u32_max(MAX_CHAINLEN);
+
/* See if there's one in the list already, including reverse */
hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[hash], hnnode) {
if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
zone, net))
goto out;
- if (chainlen++ > MAX_CHAINLEN)
+ if (chainlen++ > max_chainlen)
goto chaintoolong;
}
@@ -873,7 +901,7 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct)
if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
zone, net))
goto out;
- if (chainlen++ > MAX_CHAINLEN)
+ if (chainlen++ > max_chainlen)
goto chaintoolong;
}
@@ -1103,8 +1131,8 @@ drop:
int
__nf_conntrack_confirm(struct sk_buff *skb)
{
+ unsigned int chainlen = 0, sequence, max_chainlen;
const struct nf_conntrack_zone *zone;
- unsigned int chainlen = 0, sequence;
unsigned int hash, reply_hash;
struct nf_conntrack_tuple_hash *h;
struct nf_conn *ct;
@@ -1133,8 +1161,8 @@ __nf_conntrack_confirm(struct sk_buff *skb)
hash = *(unsigned long *)&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev;
hash = scale_hash(hash);
reply_hash = hash_conntrack(net,
- &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
-
+ &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
+ nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_REPLY));
} while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));
/* We're not in hash table, and we refuse to set up related
@@ -1168,6 +1196,7 @@ __nf_conntrack_confirm(struct sk_buff *skb)
goto dying;
}
+ max_chainlen = MIN_CHAINLEN + prandom_u32_max(MAX_CHAINLEN);
/* See if there's one in the list already, including reverse:
NAT could have grabbed it without realizing, since we're
not in the hash. If there is, we lost race. */
@@ -1175,7 +1204,7 @@ __nf_conntrack_confirm(struct sk_buff *skb)
if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
zone, net))
goto out;
- if (chainlen++ > MAX_CHAINLEN)
+ if (chainlen++ > max_chainlen)
goto chaintoolong;
}
@@ -1184,7 +1213,7 @@ __nf_conntrack_confirm(struct sk_buff *skb)
if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
zone, net))
goto out;
- if (chainlen++ > MAX_CHAINLEN) {
+ if (chainlen++ > max_chainlen) {
chaintoolong:
nf_ct_add_to_dying_list(ct);
NF_CT_STAT_INC(net, chaintoolong);
@@ -1246,7 +1275,7 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple,
rcu_read_lock();
begin:
nf_conntrack_get_ht(&ct_hash, &hsize);
- hash = __hash_conntrack(net, tuple, hsize);
+ hash = __hash_conntrack(net, tuple, nf_ct_zone_id(zone, IP_CT_DIR_REPLY), hsize);
hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[hash], hnnode) {
ct = nf_ct_tuplehash_to_ctrack(h);
@@ -1687,8 +1716,8 @@ resolve_normal_ct(struct nf_conn *tmpl,
struct nf_conntrack_tuple_hash *h;
enum ip_conntrack_info ctinfo;
struct nf_conntrack_zone tmp;
+ u32 hash, zone_id, rid;
struct nf_conn *ct;
- u32 hash;
if (!nf_ct_get_tuple(skb, skb_network_offset(skb),
dataoff, state->pf, protonum, state->net,
@@ -1699,8 +1728,20 @@ resolve_normal_ct(struct nf_conn *tmpl,
/* look for tuple match */
zone = nf_ct_zone_tmpl(tmpl, skb, &tmp);
- hash = hash_conntrack_raw(&tuple, state->net);
+
+ zone_id = nf_ct_zone_id(zone, IP_CT_DIR_ORIGINAL);
+ hash = hash_conntrack_raw(&tuple, zone_id, state->net);
h = __nf_conntrack_find_get(state->net, zone, &tuple, hash);
+
+ if (!h) {
+ rid = nf_ct_zone_id(zone, IP_CT_DIR_REPLY);
+ if (zone_id != rid) {
+ u32 tmp = hash_conntrack_raw(&tuple, rid, state->net);
+
+ h = __nf_conntrack_find_get(state->net, zone, &tuple, tmp);
+ }
+ }
+
if (!h) {
h = init_conntrack(state->net, tmpl, &tuple,
skb, dataoff, hash);
@@ -2225,28 +2266,31 @@ get_next_corpse(int (*iter)(struct nf_conn *i, void *data),
spinlock_t *lockp;
for (; *bucket < nf_conntrack_htable_size; (*bucket)++) {
+ struct hlist_nulls_head *hslot = &nf_conntrack_hash[*bucket];
+
+ if (hlist_nulls_empty(hslot))
+ continue;
+
lockp = &nf_conntrack_locks[*bucket % CONNTRACK_LOCKS];
local_bh_disable();
nf_conntrack_lock(lockp);
- if (*bucket < nf_conntrack_htable_size) {
- hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[*bucket], hnnode) {
- if (NF_CT_DIRECTION(h) != IP_CT_DIR_REPLY)
- continue;
- /* All nf_conn objects are added to hash table twice, one
- * for original direction tuple, once for the reply tuple.
- *
- * Exception: In the IPS_NAT_CLASH case, only the reply
- * tuple is added (the original tuple already existed for
- * a different object).
- *
- * We only need to call the iterator once for each
- * conntrack, so we just use the 'reply' direction
- * tuple while iterating.
- */
- ct = nf_ct_tuplehash_to_ctrack(h);
- if (iter(ct, data))
- goto found;
- }
+ hlist_nulls_for_each_entry(h, n, hslot, hnnode) {
+ if (NF_CT_DIRECTION(h) != IP_CT_DIR_REPLY)
+ continue;
+ /* All nf_conn objects are added to hash table twice, one
+ * for original direction tuple, once for the reply tuple.
+ *
+ * Exception: In the IPS_NAT_CLASH case, only the reply
+ * tuple is added (the original tuple already existed for
+ * a different object).
+ *
+ * We only need to call the iterator once for each
+ * conntrack, so we just use the 'reply' direction
+ * tuple while iterating.
+ */
+ ct = nf_ct_tuplehash_to_ctrack(h);
+ if (iter(ct, data))
+ goto found;
}
spin_unlock(lockp);
local_bh_enable();
@@ -2264,26 +2308,20 @@ found:
static void nf_ct_iterate_cleanup(int (*iter)(struct nf_conn *i, void *data),
void *data, u32 portid, int report)
{
- unsigned int bucket = 0, sequence;
+ unsigned int bucket = 0;
struct nf_conn *ct;
might_sleep();
- for (;;) {
- sequence = read_seqcount_begin(&nf_conntrack_generation);
-
- while ((ct = get_next_corpse(iter, data, &bucket)) != NULL) {
- /* Time to push up daises... */
+ mutex_lock(&nf_conntrack_mutex);
+ while ((ct = get_next_corpse(iter, data, &bucket)) != NULL) {
+ /* Time to push up daises... */
- nf_ct_delete(ct, portid, report);
- nf_ct_put(ct);
- cond_resched();
- }
-
- if (!read_seqcount_retry(&nf_conntrack_generation, sequence))
- break;
- bucket = 0;
+ nf_ct_delete(ct, portid, report);
+ nf_ct_put(ct);
+ cond_resched();
}
+ mutex_unlock(&nf_conntrack_mutex);
}
struct iter_data {
@@ -2519,8 +2557,10 @@ int nf_conntrack_hash_resize(unsigned int hashsize)
if (!hash)
return -ENOMEM;
+ mutex_lock(&nf_conntrack_mutex);
old_size = nf_conntrack_htable_size;
if (old_size == hashsize) {
+ mutex_unlock(&nf_conntrack_mutex);
kvfree(hash);
return 0;
}
@@ -2537,12 +2577,16 @@ int nf_conntrack_hash_resize(unsigned int hashsize)
for (i = 0; i < nf_conntrack_htable_size; i++) {
while (!hlist_nulls_empty(&nf_conntrack_hash[i])) {
+ unsigned int zone_id;
+
h = hlist_nulls_entry(nf_conntrack_hash[i].first,
struct nf_conntrack_tuple_hash, hnnode);
ct = nf_ct_tuplehash_to_ctrack(h);
hlist_nulls_del_rcu(&h->hnnode);
+
+ zone_id = nf_ct_zone_id(nf_ct_zone(ct), NF_CT_DIRECTION(h));
bucket = __hash_conntrack(nf_ct_net(ct),
- &h->tuple, hashsize);
+ &h->tuple, zone_id, hashsize);
hlist_nulls_add_head_rcu(&h->hnnode, &hash[bucket]);
}
}
@@ -2556,6 +2600,8 @@ int nf_conntrack_hash_resize(unsigned int hashsize)
nf_conntrack_all_unlock();
local_bh_enable();
+ mutex_unlock(&nf_conntrack_mutex);
+
synchronize_net();
kvfree(old_hash);
return 0;
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 7008961f5cb0..273117683922 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -150,13 +150,16 @@ static void __nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl)
/* We keep an extra hash for each conntrack, for fast searching. */
static unsigned int
-hash_by_src(const struct net *n, const struct nf_conntrack_tuple *tuple)
+hash_by_src(const struct net *net,
+ const struct nf_conntrack_zone *zone,
+ const struct nf_conntrack_tuple *tuple)
{
unsigned int hash;
struct {
struct nf_conntrack_man src;
u32 net_mix;
u32 protonum;
+ u32 zone;
} __aligned(SIPHASH_ALIGNMENT) combined;
get_random_once(&nf_nat_hash_rnd, sizeof(nf_nat_hash_rnd));
@@ -165,9 +168,13 @@ hash_by_src(const struct net *n, const struct nf_conntrack_tuple *tuple)
/* Original src, to ensure we map it consistently if poss. */
combined.src = tuple->src;
- combined.net_mix = net_hash_mix(n);
+ combined.net_mix = net_hash_mix(net);
combined.protonum = tuple->dst.protonum;
+ /* Zone ID can be used provided its valid for both directions */
+ if (zone->dir == NF_CT_DEFAULT_ZONE_DIR)
+ combined.zone = zone->id;
+
hash = siphash(&combined, sizeof(combined), &nf_nat_hash_rnd);
return reciprocal_scale(hash, nf_nat_htable_size);
@@ -272,7 +279,7 @@ find_appropriate_src(struct net *net,
struct nf_conntrack_tuple *result,
const struct nf_nat_range2 *range)
{
- unsigned int h = hash_by_src(net, tuple);
+ unsigned int h = hash_by_src(net, zone, tuple);
const struct nf_conn *ct;
hlist_for_each_entry_rcu(ct, &nf_nat_bysource[h], nat_bysource) {
@@ -619,7 +626,7 @@ nf_nat_setup_info(struct nf_conn *ct,
unsigned int srchash;
spinlock_t *lock;
- srchash = hash_by_src(net,
+ srchash = hash_by_src(net, nf_ct_zone(ct),
&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
lock = &nf_nat_locks[srchash % CONNTRACK_LOCKS];
spin_lock_bh(lock);
@@ -788,7 +795,7 @@ static void __nf_nat_cleanup_conntrack(struct nf_conn *ct)
{
unsigned int h;
- h = hash_by_src(nf_ct_net(ct), &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
+ h = hash_by_src(nf_ct_net(ct), nf_ct_zone(ct), &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
spin_lock_bh(&nf_nat_locks[h % CONNTRACK_LOCKS]);
hlist_del_rcu(&ct->nat_bysource);
spin_unlock_bh(&nf_nat_locks[h % CONNTRACK_LOCKS]);
diff --git a/net/netfilter/nf_nat_masquerade.c b/net/netfilter/nf_nat_masquerade.c
index 8e8a65d46345..acd73f717a08 100644
--- a/net/netfilter/nf_nat_masquerade.c
+++ b/net/netfilter/nf_nat_masquerade.c
@@ -9,8 +9,19 @@
#include <net/netfilter/nf_nat_masquerade.h>
+struct masq_dev_work {
+ struct work_struct work;
+ struct net *net;
+ union nf_inet_addr addr;
+ int ifindex;
+ int (*iter)(struct nf_conn *i, void *data);
+};
+
+#define MAX_MASQ_WORKER_COUNT 16
+
static DEFINE_MUTEX(masq_mutex);
static unsigned int masq_refcnt __read_mostly;
+static atomic_t masq_worker_count __read_mostly;
unsigned int
nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum,
@@ -63,13 +74,71 @@ nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum,
}
EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4);
-static int device_cmp(struct nf_conn *i, void *ifindex)
+static void iterate_cleanup_work(struct work_struct *work)
+{
+ struct masq_dev_work *w;
+
+ w = container_of(work, struct masq_dev_work, work);
+
+ nf_ct_iterate_cleanup_net(w->net, w->iter, (void *)w, 0, 0);
+
+ put_net(w->net);
+ kfree(w);
+ atomic_dec(&masq_worker_count);
+ module_put(THIS_MODULE);
+}
+
+/* Iterate conntrack table in the background and remove conntrack entries
+ * that use the device/address being removed.
+ *
+ * In case too many work items have been queued already or memory allocation
+ * fails iteration is skipped, conntrack entries will time out eventually.
+ */
+static void nf_nat_masq_schedule(struct net *net, union nf_inet_addr *addr,
+ int ifindex,
+ int (*iter)(struct nf_conn *i, void *data),
+ gfp_t gfp_flags)
+{
+ struct masq_dev_work *w;
+
+ if (atomic_read(&masq_worker_count) > MAX_MASQ_WORKER_COUNT)
+ return;
+
+ net = maybe_get_net(net);
+ if (!net)
+ return;
+
+ if (!try_module_get(THIS_MODULE))
+ goto err_module;
+
+ w = kzalloc(sizeof(*w), gfp_flags);
+ if (w) {
+ /* We can overshoot MAX_MASQ_WORKER_COUNT, no big deal */
+ atomic_inc(&masq_worker_count);
+
+ INIT_WORK(&w->work, iterate_cleanup_work);
+ w->ifindex = ifindex;
+ w->net = net;
+ w->iter = iter;
+ if (addr)
+ w->addr = *addr;
+ schedule_work(&w->work);
+ return;
+ }
+
+ module_put(THIS_MODULE);
+ err_module:
+ put_net(net);
+}
+
+static int device_cmp(struct nf_conn *i, void *arg)
{
const struct nf_conn_nat *nat = nfct_nat(i);
+ const struct masq_dev_work *w = arg;
if (!nat)
return 0;
- return nat->masq_index == (int)(long)ifindex;
+ return nat->masq_index == w->ifindex;
}
static int masq_device_event(struct notifier_block *this,
@@ -85,8 +154,8 @@ static int masq_device_event(struct notifier_block *this,
* and forget them.
*/
- nf_ct_iterate_cleanup_net(net, device_cmp,
- (void *)(long)dev->ifindex, 0, 0);
+ nf_nat_masq_schedule(net, NULL, dev->ifindex,
+ device_cmp, GFP_KERNEL);
}
return NOTIFY_DONE;
@@ -94,35 +163,45 @@ static int masq_device_event(struct notifier_block *this,
static int inet_cmp(struct nf_conn *ct, void *ptr)
{
- struct in_ifaddr *ifa = (struct in_ifaddr *)ptr;
- struct net_device *dev = ifa->ifa_dev->dev;
struct nf_conntrack_tuple *tuple;
+ struct masq_dev_work *w = ptr;
- if (!device_cmp(ct, (void *)(long)dev->ifindex))
+ if (!device_cmp(ct, ptr))
return 0;
tuple = &ct->tuplehash[IP_CT_DIR_REPLY].tuple;
- return ifa->ifa_address == tuple->dst.u3.ip;
+ return nf_inet_addr_cmp(&w->addr, &tuple->dst.u3);
}
static int masq_inet_event(struct notifier_block *this,
unsigned long event,
void *ptr)
{
- struct in_device *idev = ((struct in_ifaddr *)ptr)->ifa_dev;
- struct net *net = dev_net(idev->dev);
+ const struct in_ifaddr *ifa = ptr;
+ const struct in_device *idev;
+ const struct net_device *dev;
+ union nf_inet_addr addr;
+
+ if (event != NETDEV_DOWN)
+ return NOTIFY_DONE;
/* The masq_dev_notifier will catch the case of the device going
* down. So if the inetdev is dead and being destroyed we have
* no work to do. Otherwise this is an individual address removal
* and we have to perform the flush.
*/
+ idev = ifa->ifa_dev;
if (idev->dead)
return NOTIFY_DONE;
- if (event == NETDEV_DOWN)
- nf_ct_iterate_cleanup_net(net, inet_cmp, ptr, 0, 0);
+ memset(&addr, 0, sizeof(addr));
+
+ addr.ip = ifa->ifa_address;
+
+ dev = idev->dev;
+ nf_nat_masq_schedule(dev_net(idev->dev), &addr, dev->ifindex,
+ inet_cmp, GFP_KERNEL);
return NOTIFY_DONE;
}
@@ -136,8 +215,6 @@ static struct notifier_block masq_inet_notifier = {
};
#if IS_ENABLED(CONFIG_IPV6)
-static atomic_t v6_worker_count __read_mostly;
-
static int
nat_ipv6_dev_get_saddr(struct net *net, const struct net_device *dev,
const struct in6_addr *daddr, unsigned int srcprefs,
@@ -187,40 +264,6 @@ nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range,
}
EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6);
-struct masq_dev_work {
- struct work_struct work;
- struct net *net;
- struct in6_addr addr;
- int ifindex;
-};
-
-static int inet6_cmp(struct nf_conn *ct, void *work)
-{
- struct masq_dev_work *w = (struct masq_dev_work *)work;
- struct nf_conntrack_tuple *tuple;
-
- if (!device_cmp(ct, (void *)(long)w->ifindex))
- return 0;
-
- tuple = &ct->tuplehash[IP_CT_DIR_REPLY].tuple;
-
- return ipv6_addr_equal(&w->addr, &tuple->dst.u3.in6);
-}
-
-static void iterate_cleanup_work(struct work_struct *work)
-{
- struct masq_dev_work *w;
-
- w = container_of(work, struct masq_dev_work, work);
-
- nf_ct_iterate_cleanup_net(w->net, inet6_cmp, (void *)w, 0, 0);
-
- put_net(w->net);
- kfree(w);
- atomic_dec(&v6_worker_count);
- module_put(THIS_MODULE);
-}
-
/* atomic notifier; can't call nf_ct_iterate_cleanup_net (it can sleep).
*
* Defer it to the system workqueue.
@@ -233,36 +276,19 @@ static int masq_inet6_event(struct notifier_block *this,
{
struct inet6_ifaddr *ifa = ptr;
const struct net_device *dev;
- struct masq_dev_work *w;
- struct net *net;
+ union nf_inet_addr addr;
- if (event != NETDEV_DOWN || atomic_read(&v6_worker_count) >= 16)
+ if (event != NETDEV_DOWN)
return NOTIFY_DONE;
dev = ifa->idev->dev;
- net = maybe_get_net(dev_net(dev));
- if (!net)
- return NOTIFY_DONE;
- if (!try_module_get(THIS_MODULE))
- goto err_module;
+ memset(&addr, 0, sizeof(addr));
- w = kmalloc(sizeof(*w), GFP_ATOMIC);
- if (w) {
- atomic_inc(&v6_worker_count);
-
- INIT_WORK(&w->work, iterate_cleanup_work);
- w->ifindex = dev->ifindex;
- w->net = net;
- w->addr = ifa->addr;
- schedule_work(&w->work);
+ addr.in6 = ifa->addr;
- return NOTIFY_DONE;
- }
-
- module_put(THIS_MODULE);
- err_module:
- put_net(net);
+ nf_nat_masq_schedule(dev_net(dev), &addr, dev->ifindex, inet_cmp,
+ GFP_ATOMIC);
return NOTIFY_DONE;
}
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 081437dd75b7..b9546defdc28 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -4336,7 +4336,7 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
if (ops->privsize != NULL)
size = ops->privsize(nla, &desc);
alloc_size = sizeof(*set) + size + udlen;
- if (alloc_size < size)
+ if (alloc_size < size || alloc_size > INT_MAX)
return -ENOMEM;
set = kvzalloc(alloc_size, GFP_KERNEL);
if (!set)
@@ -9599,7 +9599,6 @@ static void __nft_release_table(struct net *net, struct nft_table *table)
table->use--;
nf_tables_chain_destroy(&ctx);
}
- list_del(&table->list);
nf_tables_table_destroy(&ctx);
}
@@ -9612,6 +9611,8 @@ static void __nft_release_tables(struct net *net)
if (nft_table_has_owner(table))
continue;
+ list_del(&table->list);
+
__nft_release_table(net, table);
}
}
@@ -9619,31 +9620,38 @@ static void __nft_release_tables(struct net *net)
static int nft_rcv_nl_event(struct notifier_block *this, unsigned long event,
void *ptr)
{
+ struct nft_table *table, *to_delete[8];
struct nftables_pernet *nft_net;
struct netlink_notify *n = ptr;
- struct nft_table *table, *nt;
struct net *net = n->net;
- bool release = false;
+ unsigned int deleted;
+ bool restart = false;
if (event != NETLINK_URELEASE || n->protocol != NETLINK_NETFILTER)
return NOTIFY_DONE;
nft_net = nft_pernet(net);
+ deleted = 0;
mutex_lock(&nft_net->commit_mutex);
+again:
list_for_each_entry(table, &nft_net->tables, list) {
if (nft_table_has_owner(table) &&
n->portid == table->nlpid) {
__nft_release_hook(net, table);
- release = true;
+ list_del_rcu(&table->list);
+ to_delete[deleted++] = table;
+ if (deleted >= ARRAY_SIZE(to_delete))
+ break;
}
}
- if (release) {
+ if (deleted) {
+ restart = deleted >= ARRAY_SIZE(to_delete);
synchronize_rcu();
- list_for_each_entry_safe(table, nt, &nft_net->tables, list) {
- if (nft_table_has_owner(table) &&
- n->portid == table->nlpid)
- __nft_release_table(net, table);
- }
+ while (deleted)
+ __nft_release_table(net, to_delete[--deleted]);
+
+ if (restart)
+ goto again;
}
mutex_unlock(&nft_net->commit_mutex);
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 272bcdb1392d..f69cc73c5813 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -19,6 +19,7 @@
#include <linux/netfilter_bridge/ebtables.h>
#include <linux/netfilter_arp/arp_tables.h>
#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_log.h>
/* Used for matches where *info is larger than X byte */
#define NFT_MATCH_LARGE_THRESH 192
@@ -257,8 +258,22 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
nft_compat_wait_for_destructors();
ret = xt_check_target(&par, size, proto, inv);
- if (ret < 0)
+ if (ret < 0) {
+ if (ret == -ENOENT) {
+ const char *modname = NULL;
+
+ if (strcmp(target->name, "LOG") == 0)
+ modname = "nf_log_syslog";
+ else if (strcmp(target->name, "NFLOG") == 0)
+ modname = "nfnetlink_log";
+
+ if (modname &&
+ nft_request_module(ctx->net, "%s", modname) == -EAGAIN)
+ return -EAGAIN;
+ }
+
return ret;
+ }
/* The standard target cannot be used */
if (!target->target)
diff --git a/net/netfilter/xt_LOG.c b/net/netfilter/xt_LOG.c
index 2ff75f7637b0..f39244f9c0ed 100644
--- a/net/netfilter/xt_LOG.c
+++ b/net/netfilter/xt_LOG.c
@@ -44,6 +44,7 @@ log_tg(struct sk_buff *skb, const struct xt_action_param *par)
static int log_tg_check(const struct xt_tgchk_param *par)
{
const struct xt_log_info *loginfo = par->targinfo;
+ int ret;
if (par->family != NFPROTO_IPV4 && par->family != NFPROTO_IPV6)
return -EINVAL;
@@ -58,7 +59,14 @@ static int log_tg_check(const struct xt_tgchk_param *par)
return -EINVAL;
}
- return nf_logger_find_get(par->family, NF_LOG_TYPE_LOG);
+ ret = nf_logger_find_get(par->family, NF_LOG_TYPE_LOG);
+ if (ret != 0 && !par->nft_compat) {
+ request_module("%s", "nf_log_syslog");
+
+ ret = nf_logger_find_get(par->family, NF_LOG_TYPE_LOG);
+ }
+
+ return ret;
}
static void log_tg_destroy(const struct xt_tgdtor_param *par)
diff --git a/net/netfilter/xt_NFLOG.c b/net/netfilter/xt_NFLOG.c
index fb5793208059..e660c3710a10 100644
--- a/net/netfilter/xt_NFLOG.c
+++ b/net/netfilter/xt_NFLOG.c
@@ -42,13 +42,21 @@ nflog_tg(struct sk_buff *skb, const struct xt_action_param *par)
static int nflog_tg_check(const struct xt_tgchk_param *par)
{
const struct xt_nflog_info *info = par->targinfo;
+ int ret;
if (info->flags & ~XT_NFLOG_MASK)
return -EINVAL;
if (info->prefix[sizeof(info->prefix) - 1] != '\0')
return -EINVAL;
- return nf_logger_find_get(par->family, NF_LOG_TYPE_ULOG);
+ ret = nf_logger_find_get(par->family, NF_LOG_TYPE_ULOG);
+ if (ret != 0 && !par->nft_compat) {
+ request_module("%s", "nfnetlink_log");
+
+ ret = nf_logger_find_get(par->family, NF_LOG_TYPE_ULOG);
+ }
+
+ return ret;
}
static void nflog_tg_destroy(const struct xt_tgdtor_param *par)